Selecting informative genes is one of the most important issues for deciphering biological information hidden in gene expression data. However, due to the characteristics of microarray data with small samples and large number of genes, general feature selection methods that are not biologically relevant become questionable. In this paper, we propose a novel classification method for microarray data by integrating the multi-information based gene scoring method with biological information. Through experimental evaluation, our proposed method is shown to deliver good accuracy in classification and provide biologists with deeper insights into the relations between genes and gene function categories.
|Number of pages||15|
|Journal||International Journal of Data Mining and Bioinformatics|
|State||Published - 1 Jul 2011|
- Gene expression analysis
- Gene ontology
- Gene scoring
- Microarray data classification